© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103895
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pektive
    -1.00
    lainen
    -0.91
    nipeg
    -0.89
     or
    -0.88
    関わ
    -0.88
     approve
    -0.88
    Ⅾ
    -0.86
     cuidar
    -0.82
    ෛ
    -0.82
    蠔
    -0.81
    POSITIVE LOGITS
     Шаг
    1.09
     gamle
    1.08
     skar
    1.02
    很多的
    1.01
     chrétienne
    1.00
    zule
    0.98
     Mère
    0.97
     grecque
    0.97
    eczka
    0.96
     molte
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.